Use when designing, reviewing, or classifying an agent that guards the human — defines the sentinel category, the three-part signature (S1 read-only, S2 advisory-to-human, S3 explicit honesty rule), the near-miss gallery that explains why read-only-plus-advisory is not sufficient, the honesty-rule-before-detection-logic discipline, and the three anti-patterns that eject an agent from the category
$npx -y skills add habitat-thinking/ai-literacy-superpowers --skill sentinel-designInstalls into the current project.
Run `npx skills use "https://github.com/habitat-thinking/ai-literacy-superpowers" --skill "habitat-thinking/ai-literacy-superpowers/sentinel-design"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/habitat-thinking/ai-literacy-superpowers" that are relevant to the current task. Run `npx skills add "https://github.com/habitat-thinking/ai-literacy-superpowers"` and select the relevant skills, then follow their instructions.